How to Use the Collect MCP in OpenAI Agents SDK

Q: How do agent handoffs work when managing campaigns?

You can set up a coordinator agent that runs listcampaigns to find active files. It then hands off the actual messaging task to a specialized support agent that uses sendmessage to contact the recipients.

Spin up production-grade data collection pipelines using the OpenAI Agents SDK and the Collect MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Collect MCP to OpenAI Agents SDK

Create your Vinkius account to connect Collect to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Collect with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run automated campaign checks with OpenAI Agents SDK

Your agents can now scan every active folder to track exactly what info you're missing. By calling `list_campaigns` and `get_campaign`, your OpenAI Agents SDK system maps out pending client submissions and decides which team members need to follow up. The SDK handles this by streaming tool definitions directly to your models. If an agent tries to pull data from a campaign that doesn't exist, your custom guardrails catch the error before any API calls hit our hosted endpoint.

Safe request dispatching via OpenAI guardrails

Stop worrying about rogue agents spamming your clients with duplicate files. This MCP Server lets your agent trigger structured requests using `create_request` while your Python runtime validates the recipient payload against your strict business logic. You get full visibility into every single outgoing message. The OpenAI dashboard traces how your agent uses `send_message` to nudge slow responders, keeping your communication history clean and audit-ready.

Inspect deep request metadata on the fly

When a submission comes in half-finished, your agent can drill down into the exact field that failed. It uses `get_request` and `get_element_details` to check what the user actually typed versus what your form required. This setup allows specialized agents to hand off tasks to each other. One agent detects the error in the element details, while another drafts a correction message based on your team data from `get_team_info`.

Setup guide

Set up Collect MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Collect tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Collect tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Collect tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Collect Agent",
            instructions="You have access to Collect tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Collect. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Collect now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Collect MCP in OpenAI Agents SDK

The SDK auto-discovers all ten tools when you pass our hosted URL into the server streamable HTTP constructor. You don't have to write manual schemas; your agents immediately know how to use tools like `create_request` or `list_messages`.

Yes, you can control tool access directly in your Python code before passing the server to the Agent constructor. This prevents an agent from executing `send_message` while still letting it read status updates via `get_request`.

Setting this parameter to true stops the SDK from fetching the tool definitions on every single turn. It speeds up operations like checking `get_user_info` because your agent doesn't waste latency re-learning what tools are available.

You can set up a coordinator agent that runs `list_campaigns` to find active files. It then hands off the actual messaging task to a specialized support agent that uses `send_message` to contact the recipients.

Completely. Vinkius runs the server in an isolated V8 sandbox, meaning your raw recipient requests and campaign details are never stored on our servers. The agent queries the API directly using your single endpoint token, keeping your business data private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript